designGLMM (version 0.1.0)

updateDesign_CRD: Update function for Completely Randomised Design search

Description

This function provides an update function for finding completely randomised designs. This function works by by making one or more substitutions. The number of substitutions made nd the probability of making a particular number of substitution is given in a vector of probabilities.

Usage

updateDesign_CRD(des, ntmt, sige=0,means=c(1,1), probs=c(1))

Arguments

des

a vector indicating the initial design to which we will make substitutions.

ntmt

a numeric indicating the number of treatments in the design.

sige

a numeric indicating the within block standard deviation in excess of the Poisson residual error

means

a vector specifying the means for each treatment group.

probs

a list of probabilities specifying the probability that each step of the simulated annealing substitutes a certain number of design points. The first entry corresponds to the probability that only one substitution is made in a simulated annealing step, the second is the probability that two substitutions are made and so on. By default this is set to c(1) which means that only one substitution is made in each simulated annealing step.

Value

Returns a vector containing the new design.

Details

This function is designed to work with findOptimalExactDesign, and as such shares the arguments of objfnA_CRD and objfnD_CRD. It can, however, be used on its own. The sige and means arguments are not used in this function, but are in objfnA_CRD and objfnD_CRD. If using this function on its own, then these terms may be omitted without changing the result of the function.

References

Bush, S., and Ruggiero, K. (2016) Optimal block designs for experiments with responses drawn from a Poisson distribution, Under Review, preprint available at http://arxiv.org/abs/1601.00477

See Also

findOptimalExactDesign

Examples

# Suppose that we have a completely randomised design (1,1,1,1,2,2,2,3,3,3) and would like
# to replace exactly one entry with a randomly sampled treatment. Then we set the
# probability that one entry is replaced equal to 1.

updateDesign_CRD(des=c(1,1,1,1,2,2,2,3,3,3),ntmt=3,probs=c(1))

# Now suppose that we would like to replace one entry with probability 0.6 and replace
# two entries with probability 0.4 then probs=c(0.6,0.4).

updateDesign_CRD(des=c(1,1,1,1,2,2,2,3,3,3),ntmt=3,probs=c(0.6,0.4))